Search papers, labs, and topics across Lattice.
5
0
11
Executable roles derived from team trajectories can boost multi-agent language model performance by over 16 points, reshaping agent interactions.
Visual Skill Cards transform raw interaction data into actionable insights, boosting GUI action prediction accuracy by over 11 points.
Tibetan vision-language models can now leap forward thanks to FTibSuite, a new resource suite that closes the infrastructure gap and delivers a strong baseline with substantial performance gains.
Achieve robust multimodal sentiment analysis, even with noisy or incomplete data, by explicitly modeling hierarchical relationships in hyperbolic space.
Achieve a better trade-off between search precision and carbon footprint with GaiaFlow, a framework that uses semantic-guided diffusion tuning to make neural search systems more sustainable.
